© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108476
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ت
    1.76
    т
    1.36
    ある
    1.34
     aflat
    1.25
    ا
    1.24
    ır
    1.23
    า
    1.20
    ാ
    1.16
    ாதி
    1.15
    。
    1.13
    POSITIVE LOGITS
    The
    1.42
    the
    1.42
     the
    1.16
    ina
    1.09
    ne
    0.97
    ons
    0.97
    s
    0.96
     in
    0.96
    se
    0.94
    ation
    0.94
    Activations Density 0.000%

    No Known Activations